Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 87026
    Prev
    Next
    INDEX
    Explanations

    technical scientific/math concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sticker
    -0.07
     اصول
    -0.06
     uvědom
    -0.06
     Jess
    -0.06
     jean
    -0.06
    ấp
    -0.06
     pert
    -0.06
     PC
    -0.06
     Another
    -0.06
     unde
    -0.06
    POSITIVE LOGITS
     EventArgs
    0.07
     posled
    0.07
    leneck
    0.07
    _variable
    0.07
     buluş
    0.06
    旁
    0.06
    esehen
    0.06
     evidenced
    0.06
    ره
    0.06
    inium
    0.06
    Activations Density 0.088%

    No Known Activations